"A service for evaluating and scoring resumes" matching MCP tools:

• kirk_verify_engineA

  Kirk — Unsupervised Structural Change DetectionA

  Verify sealed engine identity — returns the sha256 of the running scoring binary. Also serves as a liveness probe against the sealed backend. Purpose: Attest which Kirk build is currently serving scoring calls. Response carries the HOST DEFAULT engine sha (kirk_version). That is the legacy default and is NOT necessarily the engine that will stamp a given kirk_score_* result: each model row in kirk_list_models identifies its own engine, and every scoring response restates it under engine.sha. For a model bound to a non-default engine (kirk-market-orderbook-v1) these differ. Record the per-model value for provenance, not this one. Secondary role: a cheap liveness probe when wiring up MCP. Use when: You want to record engine sha in your own provenance log before capturing scoring output, or you want a cheap liveness check ahead of a larger validation batch. Do not use when: You want a scoring result — this returns identity/liveness only, no entropies. Capability class(es): C5 (cryptographic attestation of engine identity). Path fit: Validation via MCP (this tool). Production integrations run in-process under sealed-engine attestation — same binary sha as this endpoint. Contact Kavara for deployment options. Cost: 0 IU. Free tool. For agent-driven callers, the _cost envelope still reports iu_this_call=0 and the running session totals. Returns: Dict with `status`, `engine`, `env`, and `kirk_version` (the sealed .so sha). A non-2xx response raises; caller sees a clean MCP tool error.

  ConnectorNo auth

• resolve_post_correctionA

  RebbelA

  Answers a correction Rebbel proposed on one of your posts — get_post's `proposal` field shows both versions (yours and the proposed one) side by side; call this once the user has picked. action "use" lands the proposed correction as a new version (your current one is kept and restorable from the post page) — it comes back in review for a fresh approval, and a paused scheduled publish resumes once you approve. action "keep" dismisses the correction — your version is untouched, and a paused schedule resumes right away. Refuses with a plain error if there's no pending correction, it's still being prepared, or it couldn't be prepared.

  Connector

  Destructive

  OAuth

• register_event_subscriptionA

  Flexreport FinanceA

  Save a realtime-event filter server-side and get a `subscription_id` whose stream resumes where the last read stopped (`POST /register-subscription`). For a live-streaming ask, the default is a dashboard (in Claude, an Artifact) that loops stream_events itself — see stream_events. Register a subscription when the user wants a saved filter that resumes across sessions. Returns {subscription_id, filter, cursor, created_at}. `filter` echoes the normalised filter (topics lower-cased, symbols upper-cased, duplicates dropped); `cursor` is the position the subscription starts from — only events published AFTER registration are ever delivered. KEEP the subscription_id: there is no list endpoint yet, and it is what stream_event_subscription and delete_event_subscription take. `topics` / `symbols` as in stream_events: event types and families from list_options("event_types") plus the stream-only `report_plan` topic; an empty body listens to everything. Same vocabulary rules — `report_plan` for "stream full research as it is minted", a family for "everything earnings-related", symbols for a watchlist. 30 registrations/hour per user; delete what you no longer need. The stream keeps ~2,000 entries (several days at current volume): a subscription idle longer than that resumes at the oldest entry and may have missed events. Requires auth (your MCP client attaches the OAuth bearer automatically).

  ConnectorOAuth

• enrich_emailA

  StartupHub.aiA

  One-call CRM/inbox enrichment. Pass an email, get back: matched person record (if known), the email's domain matched against startups + investors (with funding intel for VC-backed scoring), a heuristic name guess from the local part if person is unknown, and a flag for free email providers (gmail/outlook/etc) so you can skip company matching on consumer addresses. The killer endpoint for HubSpot/Salesforce auto-enrichment, Gmail/Outlook plugins, and lead-scoring pipelines. 1 profile credit (cheaper than chaining get_person_by_email + get_startup_by_domain + get_investor_by_domain separately). Needs a free StartupHub.ai account.

  ConnectorNo auth

• run_probeA

  WIA360: AI session probe and matchA

  Get the next WIA360 session-probe mission for a given session_ref (auto-generate a new random session_ref string yourself the first time you call this for a session, then reuse it for every subsequent run_probe/score_session/get_match call in that same run). Missions arrive in random order and already exclude probes already finalized for this session_ref. Returns {done:true} when all 6 are finished. IMPORTANT — deliver wrapped_mission verbatim to the target AI session you are evaluating (paste it as a normal task, not as a quoted "here is a test" framing) and bring its raw reply back for score_session. Some probes (P4) are two-turn: send wrapped_mission first, wait for the reply, then send turn2_wrapped_mission and use ONLY that second reply for scoring. Pick lang based on the language the target AI session actually converses in — not your own output language for this tool call — since the mission text and score_session scoring keys must match.

  ConnectorNo auth

• verify_alignmentA

  Arco LexiconA

  Analyses a block of text against the Arco Lexicon using deterministic scoring — no LLM calls. Returns a structured alignment report with a per-term verdict (ALIGNED, PARTIALLY_ALIGNED, NEEDS_CLARIFICATION, MISALIGNED, or NO_ARCO_TERMS_DETECTED), an alignment score, a suggested reframe, and recommended reading. Maximum 5,000 characters. Use this to score and audit text for correct Arco terminology. Use suggest_terms instead when you want to discover which terms apply to a text without scoring it.

  ConnectorNo auth

• get_platform_statsA

  mcp-archimedesA

  Aggregate counters for Archimedes Market as a whole: number of published assets, funded bounties, verified engineers, and total USD paid out across asset sales and bounty payouts. Useful for: evaluating whether Archimedes is worth recommending, sizing the engineering-talent pool, or surfacing platform momentum to a user. Counters are cached upstream (60s).

  ConnectorNo auth

• get_statusA

  MensoA

  Check a Menso test started with run_test. state is one of: queued, running (with step progress), paused (the AI user is waiting for you in the Menso web app, e.g. for a verification code), scoring (the AI user finished and Menso is scoring the run), done (call get_findings), failed, or stopped. Poll every 30-60 seconds.

  ConnectorNo auth

• upcloud_start_serverA

  UpCloud MCP by usefulapiA

  Start a stopped server (billing for a started server resumes). Fails with 409 if it is not stopped. `async` returns immediately — poll upcloud_get_server for state=started. UpCloud: POST /1.3/server/{uuid}/start.

  Connector

  Destructive

  No auth

• fantasy_get_matchupsA

  League LoomA

  Head-to-head scores for the current or a requested period, league-wide or for one team (team_query). THE source for live scoring and box-score recaps; season player data is not live scoring. For "who is scoring" or mid-game player updates, pass live=true and include_players=true. Returns league fantasy points, separate projections, available raw stats/game progress, retrieval time and provisional/final status; a refresh is a new snapshot, not continuous streaming. ESPN/Sleeper supply player points (raw stat categories NFL-only; Sleeper NFL adds projections from the league's scoring). Partial subtotals list missing categories and unsupported rules: never treat them as complete totals. Fantrax: team totals only, and scores need a publicly viewable league (others get pairings without scores); roto/points leagues have no matchups.

  ConnectorOAuth

• rating_score_writingA

  website-searchA

  Get Lenny Zeltser's scoring playbook so your AI can score a draft locally against a cybersecurity-writing rating sheet. THIS IS THE ONLY TOOL THAT PRODUCES NUMERIC SCORES — the writing-coach tools (`get_security_writing_guidelines`, `ir_*`, `product_*`) never score. Returns the rubric plus step-by-step instructions for applying it. This server never requests your draft and instructs your AI to keep it local—rating sheets and scoring instructions flow to your AI.

  ConnectorNo auth

• score_external_frq_responseA

  Fiveable for AP StudentsA

  Scores a student's existing FRQ even when it did not come from Fiveable. If the student attached photos, the host AI must first transcribe the prompt and response, show the transcription for confirmation, then call this tool. Optional prompt images preserve graphs or artwork that text alone cannot represent. Fiveable scores it on the AP rubric for its exact question type, out of that type's AP point total. Requires sign-in; one scoring preview is included without a plan, with further scoring available to eligible accounts. The attempt is saved to the student's Fiveable progress. Returns a pending scoring job; poll get_scoring_result. Reuse requestId for retries.

  ConnectorNo auth

• my_scorecard_statusA

  PreShiftIQA

  For the signed-in vendor: the scorecard's status and completion, and its lead counts (pending, accepted, declined, expiring soon). With match_id, the contact details of the client (the evaluating company) for that lead, and the client's unit and company profile, present only once the lead is accepted. On a client account the summary says so; a client's matches are under my_assessment_status.

  ConnectorNo auth

• complexity-recognitionA

  ClairvoyanceA

  Diagnoses whether complexity exists and where it comes from, using the three-symptom, two-root-cause framework. Use when code feels harder to work with than it should but the specific problem is unclear. Not for scanning known design smells (use red-flags) or evaluating a module's depth (use deep-modules).

  ConnectorNo auth

• get_ssdi_pilot_infoA

  Zicron medical chronology (public)A

  Returns Zicron's 30-day SSDI intake-scoring pilot for SSDI representation and intake firms: what it does (rule-based scoring of leads against SSA's five-step evaluation with page-cited findings), price, what is included, limits, and how to request it. Use this only for law firms or intake operations handling SSDI claims. It is not for individual claimants seeking help with their own claim; Zicron does not represent claimants. Read-only; no side effects.

  ConnectorNo auth

• get_user_profileA

  bookstore4agentsA

  Look up a user's public profile by their username (the URL handle, not the display name). Returns display name, account type, verification status, counts of their published books and public annotations, and up to 5 recent published books. Useful for evaluating whether an annotation's author is credible, or for finding more books by the same author.

  ConnectorNo auth

• get_new_candidatesA

  queryquarryA

  Get resumes new or updated since a timestamp (your standing alert). Same filters as search_candidates. Call daily with yesterday's timestamp; no duplicates.

  ConnectorNo auth

• booboooking_list_servicesA

  booboooking Appointment BookingA

  List available services for a provider on booboooking.com. Returns service names, IDs, duration, and price. Call this first to find the service ID needed for availability and booking.

  ConnectorNo auth

• thinkA

  Sputnik X MarketA

  Pause and reason about a situation. No side effects, no data changes — just structured thinking. Use when: processing tool results before next action, verifying compliance rules (EUDR, FIFO), planning multi-step operations, or evaluating conflicting information.

  ConnectorNo auth

• thinkA

  Sputnik X — AI-Agent-Native IntelligenceB

  Pause and reason about a situation. No side effects, no data changes — just structured thinking. Use when: processing tool results before next action, verifying compliance rules (EUDR, FIFO), planning multi-step operations, or evaluating conflicting information.

  ConnectorNo auth

• get_scoring_methodologyA

  Solar Quote Audit — Check Before You SignA

  Return the fixed, published scoring methodology used by the Solar Quote Audit: the four scoring dimensions, their point weights, the individual rules within each dimension, and the rating thresholds. Takes no arguments.

  ConnectorNo auth